diff options
Diffstat (limited to 'src/libexpr/eval.cc')
| -rw-r--r-- | src/libexpr/eval.cc | 228 |
1 files changed, 139 insertions, 89 deletions
diff --git a/src/libexpr/eval.cc b/src/libexpr/eval.cc index 517952164a97..ab407e56907c 100644 --- a/src/libexpr/eval.cc +++ b/src/libexpr/eval.cc @@ -6,27 +6,26 @@ #include "globals.hh" #include "eval-inline.hh" #include "download.hh" +#include "json.hh" #include <algorithm> #include <cstring> #include <unistd.h> #include <sys/time.h> #include <sys/resource.h> +#include <iostream> +#include <fstream> + +#include <sys/time.h> +#include <sys/resource.h> #if HAVE_BOEHMGC #include <gc/gc.h> #include <gc/gc_cpp.h> -#define NEW new (UseGC) - -#else - -#define NEW new - #endif - namespace nix { @@ -34,7 +33,7 @@ static char * dupString(const char * s) { char * t; #if HAVE_BOEHMGC - t = GC_strdup(s); + t = GC_STRDUP(s); #else t = strdup(s); #endif @@ -43,20 +42,6 @@ static char * dupString(const char * s) } -/* Note: Various places expect the allocated memory to be zeroed. */ -static void * allocBytes(size_t n) -{ - void * p; -#if HAVE_BOEHMGC - p = GC_malloc(n); -#else - p = calloc(n, 1); -#endif - if (!p) throw std::bad_alloc(); - return p; -} - - static void printValue(std::ostream & str, std::set<const Value *> & active, const Value & v) { checkInterrupt(); @@ -199,8 +184,15 @@ void initGC() #if HAVE_BOEHMGC /* Initialise the Boehm garbage collector. */ + + /* Don't look for interior pointers. This reduces the odds of + misdetection a bit. */ GC_set_all_interior_pointers(0); + /* We don't have any roots in data segments, so don't scan from + there. */ + GC_set_no_dls(1); + GC_INIT(); GC_set_oom_fn(oomHandler); @@ -346,7 +338,6 @@ EvalState::EvalState(const Strings & _searchPath, ref<Store> store) EvalState::~EvalState() { - fileEvalCache.clear(); } @@ -360,19 +351,25 @@ Path EvalState::checkSourcePath(const Path & path_) bool found = false; + /* First canonicalize the path without symlinks, so we make sure an + * attacker can't append ../../... to a path that would be in allowedPaths + * and thus leak symlink targets. + */ + Path abspath = canonPath(path_); + for (auto & i : *allowedPaths) { - if (isDirOrInDir(path_, i)) { + if (isDirOrInDir(abspath, i)) { found = true; break; } } if (!found) - throw RestrictedPathError("access to path '%1%' is forbidden in restricted mode", path_); + throw RestrictedPathError("access to path '%1%' is forbidden in restricted mode", abspath); /* Resolve symlinks. */ - debug(format("checking access to '%s'") % path_); - Path path = canonPath(path_, true); + debug(format("checking access to '%s'") % abspath); + Path path = canonPath(abspath, true); for (auto & i : *allowedPaths) { if (isDirOrInDir(path, i)) { @@ -451,7 +448,7 @@ Value * EvalState::addPrimOp(const string & name, string name2 = string(name, 0, 2) == "__" ? string(name, 2) : name; Symbol sym = symbols.create(name2); v->type = tPrimOp; - v->primOp = NEW PrimOp(primOp, arity, sym); + v->primOp = new PrimOp(primOp, arity, sym); staticBaseEnv.vars[symbols.create(name)] = baseEnvDispl; baseEnv.values[baseEnvDispl++] = v; baseEnv.values[0]->attrs->push_back(Attr(sym, v)); @@ -589,10 +586,19 @@ inline Value * EvalState::lookupVar(Env * env, const ExprVar & var, bool noEval) } +std::atomic<uint64_t> nrValuesFreed{0}; + +void finalizeValue(void * obj, void * data) +{ + nrValuesFreed++; +} + Value * EvalState::allocValue() { nrValues++; - return (Value *) allocBytes(sizeof(Value)); + auto v = (Value *) allocBytes(sizeof(Value)); + //GC_register_finalizer_no_order(v, finalizeValue, nullptr, nullptr, nullptr); + return v; } @@ -725,7 +731,17 @@ void EvalState::evalFile(const Path & path_, Value & v) } printTalkative("evaluating file '%1%'", path2); - Expr * e = parseExprFromFile(checkSourcePath(path2)); + Expr * e = nullptr; + + auto j = fileParseCache.find(path2); + if (j != fileParseCache.end()) + e = j->second; + + if (!e) + e = parseExprFromFile(checkSourcePath(path2)); + + fileParseCache[path2] = e; + try { eval(e, v); } catch (Error & e) { @@ -1068,6 +1084,8 @@ void EvalState::callPrimOp(Value & fun, Value & arg, Value & v, const Pos & pos) void EvalState::callFunction(Value & fun, Value & arg, Value & v, const Pos & pos) { + forceValue(fun, pos); + if (fun.type == tPrimOp || fun.type == tPrimOpApp) { callPrimOp(fun, arg, v, pos); return; @@ -1083,10 +1101,8 @@ void EvalState::callFunction(Value & fun, Value & arg, Value & v, const Pos & po auto & fun2 = *allocValue(); fun2 = fun; /* !!! Should we use the attr pos here? */ - forceValue(*found->value, pos); Value v2; callFunction(*found->value, fun2, v2, pos); - forceValue(v2, pos); return callFunction(v2, arg, v, pos); } } @@ -1173,7 +1189,6 @@ void EvalState::autoCallFunction(Bindings & args, Value & fun, Value & res) if (fun.type == tAttrs) { auto found = fun.attrs->find(sFunctor); if (found != fun.attrs->end()) { - forceValue(*found->value); Value * v = allocValue(); callFunction(*found->value, fun, *v, noPos); forceValue(*v); @@ -1557,7 +1572,6 @@ string EvalState::coerceToString(const Pos & pos, Value & v, PathSet & context, if (v.type == tAttrs) { auto i = v.attrs->find(sToString); if (i != v.attrs->end()) { - forceValue(*i->value, pos); Value v1; callFunction(*i->value, v, v1, pos); return coerceToString(pos, v1, context, coerceMore, copyToStore); @@ -1711,12 +1725,9 @@ bool EvalState::eqValues(Value & v1, Value & v2) } } - void EvalState::printStats() { bool showStats = getEnv("NIX_SHOW_STATS", "0") != "0"; - Verbosity v = showStats ? lvlInfo : lvlDebug; - printMsg(v, "evaluation statistics:"); struct rusage buf; getrusage(RUSAGE_SELF, &buf); @@ -1727,62 +1738,101 @@ void EvalState::printStats() uint64_t bValues = nrValues * sizeof(Value); uint64_t bAttrsets = nrAttrsets * sizeof(Bindings) + nrAttrsInAttrsets * sizeof(Attr); - printMsg(v, format(" time elapsed: %1%") % cpuTime); - printMsg(v, format(" size of a value: %1%") % sizeof(Value)); - printMsg(v, format(" size of an attr: %1%") % sizeof(Attr)); - printMsg(v, format(" environments allocated count: %1%") % nrEnvs); - printMsg(v, format(" environments allocated bytes: %1%") % bEnvs); - printMsg(v, format(" list elements count: %1%") % nrListElems); - printMsg(v, format(" list elements bytes: %1%") % bLists); - printMsg(v, format(" list concatenations: %1%") % nrListConcats); - printMsg(v, format(" values allocated count: %1%") % nrValues); - printMsg(v, format(" values allocated bytes: %1%") % bValues); - printMsg(v, format(" sets allocated: %1% (%2% bytes)") % nrAttrsets % bAttrsets); - printMsg(v, format(" right-biased unions: %1%") % nrOpUpdates); - printMsg(v, format(" values copied in right-biased unions: %1%") % nrOpUpdateValuesCopied); - printMsg(v, format(" symbols in symbol table: %1%") % symbols.size()); - printMsg(v, format(" size of symbol table: %1%") % symbols.totalSize()); - printMsg(v, format(" number of thunks: %1%") % nrThunks); - printMsg(v, format(" number of thunks avoided: %1%") % nrAvoided); - printMsg(v, format(" number of attr lookups: %1%") % nrLookups); - printMsg(v, format(" number of primop calls: %1%") % nrPrimOpCalls); - printMsg(v, format(" number of function calls: %1%") % nrFunctionCalls); - printMsg(v, format(" total allocations: %1% bytes") % (bEnvs + bLists + bValues + bAttrsets)); - #if HAVE_BOEHMGC GC_word heapSize, totalBytes; GC_get_heap_usage_safe(&heapSize, 0, 0, 0, &totalBytes); - printMsg(v, format(" current Boehm heap size: %1% bytes") % heapSize); - printMsg(v, format(" total Boehm heap allocations: %1% bytes") % totalBytes); #endif - - if (countCalls) { - v = lvlInfo; - - printMsg(v, format("calls to %1% primops:") % primOpCalls.size()); - typedef std::multimap<size_t, Symbol> PrimOpCalls_; - PrimOpCalls_ primOpCalls_; - for (auto & i : primOpCalls) - primOpCalls_.insert(std::pair<size_t, Symbol>(i.second, i.first)); - for (auto i = primOpCalls_.rbegin(); i != primOpCalls_.rend(); ++i) - printMsg(v, format("%1$10d %2%") % i->first % i->second); - - printMsg(v, format("calls to %1% functions:") % functionCalls.size()); - typedef std::multimap<size_t, ExprLambda *> FunctionCalls_; - FunctionCalls_ functionCalls_; - for (auto & i : functionCalls) - functionCalls_.insert(std::pair<size_t, ExprLambda *>(i.second, i.first)); - for (auto i = functionCalls_.rbegin(); i != functionCalls_.rend(); ++i) - printMsg(v, format("%1$10d %2%") % i->first % i->second->showNamePos()); - - printMsg(v, format("evaluations of %1% attributes:") % attrSelects.size()); - typedef std::multimap<size_t, Pos> AttrSelects_; - AttrSelects_ attrSelects_; - for (auto & i : attrSelects) - attrSelects_.insert(std::pair<size_t, Pos>(i.second, i.first)); - for (auto i = attrSelects_.rbegin(); i != attrSelects_.rend(); ++i) - printMsg(v, format("%1$10d %2%") % i->first % i->second); - + if (showStats) { + auto outPath = getEnv("NIX_SHOW_STATS_PATH","-"); + std::fstream fs; + if (outPath != "-") + fs.open(outPath, std::fstream::out); + JSONObject topObj(outPath == "-" ? std::cerr : fs, true); + topObj.attr("cpuTime",cpuTime); + { + auto envs = topObj.object("envs"); + envs.attr("number", nrEnvs); + envs.attr("elements", nrValuesInEnvs); + envs.attr("bytes", bEnvs); + } + { + auto lists = topObj.object("list"); + lists.attr("elements", nrListElems); + lists.attr("bytes", bLists); + lists.attr("concats", nrListConcats); + } + { + auto values = topObj.object("values"); + values.attr("number", nrValues); + values.attr("bytes", bValues); + } + { + auto syms = topObj.object("symbols"); + syms.attr("number", symbols.size()); + syms.attr("bytes", symbols.totalSize()); + } + { + auto sets = topObj.object("sets"); + sets.attr("number", nrAttrsets); + sets.attr("bytes", bAttrsets); + sets.attr("elements", nrAttrsInAttrsets); + } + { + auto sizes = topObj.object("sizes"); + sizes.attr("Env", sizeof(Env)); + sizes.attr("Value", sizeof(Value)); + sizes.attr("Bindings", sizeof(Bindings)); + sizes.attr("Attr", sizeof(Attr)); + } + topObj.attr("nrOpUpdates", nrOpUpdates); + topObj.attr("nrOpUpdateValuesCopied", nrOpUpdateValuesCopied); + topObj.attr("nrThunks", nrThunks); + topObj.attr("nrAvoided", nrAvoided); + topObj.attr("nrLookups", nrLookups); + topObj.attr("nrPrimOpCalls", nrPrimOpCalls); + topObj.attr("nrFunctionCalls", nrFunctionCalls); +#if HAVE_BOEHMGC + { + auto gc = topObj.object("gc"); + gc.attr("heapSize", heapSize); + gc.attr("totalBytes", totalBytes); + } +#endif + if (countCalls) { + { + auto obj = topObj.object("primops"); + for (auto & i : primOpCalls) + obj.attr(i.first, i.second); + } + { + auto list = topObj.list("functions"); + for (auto & i : functionCalls) { + auto obj = list.object(); + if (i.first->name.set()) + obj.attr("name", (const string &) i.first->name); + else + obj.attr("name", nullptr); + if (i.first->pos) { + obj.attr("file", (const string &) i.first->pos.file); + obj.attr("line", i.first->pos.line); + obj.attr("column", i.first->pos.column); + } + obj.attr("count", i.second); + } + } + { + auto list = topObj.list("attributes"); + for (auto & i : attrSelects) { + auto obj = list.object(); + if (i.first) { + obj.attr("file", (const string &) i.first.file); + obj.attr("line", i.first.line); + obj.attr("column", i.first.column); + } + obj.attr("count", i.second); + } + } + } } } |